Qwen 3.5 397B-A17B
LLM Provider / Model ยท Frontier open-weight reasoning, native multimodal tasks (text/image/video co-trained), commercial use under Apache 2.0, Alibaba Cloud Model Studio (1M ctx hosted)
At a glance
| Input price | Free (self-hosted) |
| Output price | Free (self-hosted) |
| Price tier | Free |
| Context window | 256K |
| Max output | 32K |
| Context tier | 128K-500K |
| Speed tier | Standard |
| Latency | local-bound |
| Knowledge cutoff | Dec 2025 |
| Modality | Multimodal (vision) |
| Model ID | qwen3.5-397b-a17b |
| Provider | Alibaba |
| HumanEval | 91% |
| MMLU | 87% |
| SWE-Bench | 71% |
| Benchmark | GDPval-AA: top open |
| Released | Feb 2026 |
| Hosting | Open-weights |
| Capabilities | Vision, Tool use, Streaming, Structured output, MoE (397B / 17B active, 512 experts), Native multimodal training, Function calling, Apache 2.0, Self-hostable |
What Qwen 3.5 397B-A17B does
Vision, Tool use, Streaming, Structured output, MoE (397B / 17B active, 512 experts), Native multimodal training, Function calling, Apache 2.0, Self-hostable
Best for
Frontier open-weight reasoning, native multimodal tasks (text/image/video co-trained), commercial use under Apache 2.0, Alibaba Cloud Model Studio (1M ctx hosted)
Works well with
Agent / Orchestration
Conflicts & caveats
- Trae's built-in model menu may not include Qwen 3.5 397B-A17B โ Trae primarily ships with Claude/GPT/Gemini/DeepSeek.
- Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but Qwen 3.5 397B-A17B is not in the supported model list.
- Kiro's spec mode is tuned for Claude models โ Qwen 3.5 397B-A17B may work but spec-driven flows are best with Claude.
- Cursor's built-in model menu may not include Qwen 3.5 397B-A17B โ verify it's available in your Cursor model picker.
- OpenAI Codex (VS Code) is tied to OpenAI's GPT-5.1 Codex family โ Qwen 3.5 397B-A17B is not selectable inside this integration.
- Gemini CLI is locked to Google Gemini models โ your LLM is Qwen 3.5 397B-A17B.
- Privacy conflict: Self-hosted Qwen 3.5 397B-A17B sends code to cloud @codebase (Cursor). Use local context (Continue indexing, ChromaDB, LanceDB, pgvector, Vespa self-hosted) for true privacy.
- Claude Code only works with Claude models โ your LLM is Qwen 3.5 397B-A17B.
- Devin uses Cognition's proprietary model internally โ your selected Qwen 3.5 397B-A17B will be ignored.
- OpenAI Codex (Cloud) runs GPT-5.1 Codex internally โ your selected Qwen 3.5 397B-A17B will be ignored.
- Jules runs Gemini models internally โ your selected Qwen 3.5 397B-A17B will be ignored.
- The Claude Code SDK is tuned for Claude models โ Qwen 3.5 397B-A17B may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
- Lovable uses a fixed internal model โ your selected Qwen 3.5 397B-A17B will be ignored.
- Replit Agent 3 uses its own model selection internally โ your selected Qwen 3.5 397B-A17B will be ignored.
Build a full stack around Qwen 3.5 397B-A17B โ Flowpicker shows compatibility warnings before you commit.
Open the stack planner โ